INDEX

Explanations

text from technical documents including patents, code, and research papers

oai_token-act-pair · gemini-2.0-flash

Code/technical text

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Portail

-0.85

SOUNDBITE

-0.78

Hochspringen

-0.74

PreferredItem

-0.74

RectangleBorder

-0.73

 continúas

-0.72

}")

-0.71

"])

-0.71

SequentialGroup

-0.69

)";

-0.69

POSITIVE LOGITS

endola

0.48

 Dalio

0.42

 الحره

0.42

 esat

0.42

 Breakdown

0.41

 politiche

0.41

 Preven

0.40

 BLOOD

0.40

 coser

0.40

วัด

0.40

Activations Density 0.057%

text from technical documents including patents, code, and research papers

Code/technical text

No Comments

No Known Activations